-
1.发明授权公开(公告)号：US11170897B2
公开(公告)日：2021-11-09
申请号：US16488029
申请日：2017-02-23
Applicant: Google LLC
Inventor： Martin Christian Stumpe , Lily Peng , Yun Liu , Krishna K. Gadepalli , Timo Kohlberger
Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated. Each of the patches is assigned a color or grayscale value in accordance with (1) the likelihood of malignancy score assigned to the patch by the combined outputs of the ensemble of deep neural network pattern recognizers and (2) a code which assigns distinct colors (or grayscale values) to different values of likelihood of malignancy scores assigned to the patches.
-
2.发明申请公开(公告)号：US20190340468A1
公开(公告)日：2019-11-07
申请号：US15972929
申请日：2018-05-07
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
3.发明申请公开(公告)号：US20220027678A1
公开(公告)日：2022-01-27
申请号：US17493066
申请日：2021-10-04
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
Patent Agency Ranking
4.发明申请公开(公告)号：US20200285908A1
公开(公告)日：2020-09-10
申请号：US16883014
申请日：2020-05-26
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
5.发明授权公开(公告)号：US10706328B2
公开(公告)日：2020-07-07
申请号：US15972929
申请日：2018-05-07
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
6.发明授权公开(公告)号：US11657487B2
公开(公告)日：2023-05-23
申请号：US17493066
申请日：2021-10-04
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
CPC classification number: G06T7/0002 , G06F18/217 , G06N3/08 , G06N20/00 , G06V20/693 , G06V20/698 , G16H30/40 , G06V2201/03
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
7.发明授权公开(公告)号：US11164048B2
公开(公告)日：2021-11-02
申请号：US16883014
申请日：2020-05-26
Applicant: Google LLC
Inventor： Martin Stumpe , Timo Kohlberger
Abstract: A method is described for generating a prediction of a disease classification error for a magnified, digital microscope slide image of a tissue sample. The image is composed of a multitude of patches or tiles of pixel image data. An out-of-focus degree per patch is computed using a machine learning out-of-focus classifier. Data representing expected disease classifier error statistics of a machine learning disease classifier for a plurality of out-of-focus degrees is retrieved. A mapping of the expected disease classifier error statistics to each of the patches of the digital microscope slide image based on the computed out-of-focus degree per patch is computed, thereby generating a disease classifier error prediction for each of the patches. The disease classifier error predictions thus generated are aggregated over all of the patches.
-
8.发明申请公开(公告)号：US20200066407A1
公开(公告)日：2020-02-27
申请号：US16488029
申请日：2017-02-23
Applicant: Google LLC
Inventor： Martin Christian Stumpe , Lily Peng , Yun Liu , Krishna K. Gadepalli , Timo Kohlberger
Abstract: A method, system and machine for assisting a pathologist in identifying the presence of tumor cells in lymph node tissue is disclosed. The digital image of lymph node tissue at a first magnification (e.g., 40×) is subdivided into a multitude of rectangular “patches.” A likelihood of malignancy score is then determined for each of the patches. The score is obtained by analyzing pixel data from the patch (e.g., pixel data centered on and including the patch) using a computer system programmed as an ensemble of deep neural network pattern recognizers, each operating on different magnification levels of the patch. A representation or “heatmap” of the slide is generated. Each of the patches is assigned a color or grayscale value in accordance with (1) the likelihood of malignancy score assigned to the patch by the combined outputs of the ensemble of deep neural network pattern recognizers and (2) a code which assigns distinct colors (or grayscale values) to different values of likelihood of malignancy scores assigned to the patches.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.02 seconds)
